让图像每个像素自适应调整去噪强度，提升低剂量CT清晰度。
Learnable Total Variation with Lambda Mapping for Low-Dose CT Denoising
- 用可学习的参数图替代固定值，实现像素级去噪强度调节。
- 在真实模拟数据上比传统方法最高提升3.7dB PSNR和8% SSIM。
- 结果可解释，适合需要可信重建的医学影像场景。
虽然总变差（TV）在降噪和边缘保持方面表现优异，但其依赖标量正则化参数限制了自适应性。本文提出可学习总变差（LTV）框架，将展开的TV求解器与预测逐像素正则化图的LambdaNet结合。该框架端到端训练，联合优化重建与正则化，实现空间自适应平滑。在基于真实LoDoPaB-CT模拟数据的DeepLesion数据集上实验显示，相比经典TV和FBP+U-Net，LTV持续取得提升，最高达+3.7 dB PSNR和8%相对SSIM改善。LTV为低剂量CT去噪提供了可解释的黑箱CNN替代方案。
原文摘要 · Abstract (English)
While Total Variation (TV) excels in noise reduction and edge preservation, its reliance on a scalar regularization parameter limits adaptivity. In this study, we present a Learnable Total Variation (LTV) framework coupling an unrolled TV solver with a LambdaNet that predicts a per-pixel regularization map. The proposed framework is trained end-to-end to optimize reconstruction and regularization jointly, yielding spatially adaptive smoothing. Experiments on the DeepLesion dataset, using realistic LoDoPaB-CT simulation, show consistent gains over classical TV and FBP+U-Net, achieving up to +3.7 dB PSNR and 8% relative SSIM improvement. LTV provides an interpretable alternative to black-box CNNs for low-dose CT denoising.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。